公开(公告)号：US11922489B2

公开(公告)日：2024-03-05

申请号：US16272902

申请日：2019-02-11

Applicant: A9.com, Inc.

Inventor： Rupa Chaturvedi ,  Xing Zhang ,  Frank Partalis ,  Yu Lou ,  Colin Jon Taylor ,  Simon Fox

IPC: G06T19/00 ,  G06F3/04847 ,  G06N3/084 ,  G06Q30/0251 ,  G06Q30/0601 ,  G06T7/50 ,  A61B90/00

CPC classification number: G06Q30/0643 ,  G06F3/04847 ,  G06N3/084 ,  G06Q30/0257 ,  G06Q30/0633 ,  G06T7/50 ,  G06T19/006 ,  A61B2090/365 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A camera is used to capture image data of representations of a physical environment. Planes and surfaces are determined from a representation. The planes and the surfaces are analyzed using relationships there between to obtain shapes and depth information for available spaces within the physical environment. Locations of the camera with respect to the physical environment are determined. The shapes and the depth information are analyzed using a trained neural network to determine items fitting the available spaces. A live camera view is overlaid with a selection from the items to provide an augmented reality (AR) view of the physical environment from an individual location of the locations. The AR view is enabled so that a user can port to a different location than the individual location by an input received to the AR view while the selection from the items remains anchored to the individual location.

公开(公告)号：US11495003B1

公开(公告)日：2022-11-08

申请号：US17106669

申请日：2020-11-30

Applicant: A9.com, Inc.

Inventor： Mukul Agarwal ,  Jonathan Bernadel-Huey ,  Kevin May ,  Xing Zhang ,  Karl Hillesland ,  Jack Mousseau ,  Simon Fox

IPC: G06T19/20 ,  G06T19/00 ,  G06Q30/06 ,  G06F3/01

Abstract: Techniques for placing and manipulating multiple three-dimensional (3D) models using mobile augmented reality (AR) are described. One technique includes receiving a first request to initialize an AR simulation of a first product for sale within a physical environment. In response to the first request, a first 3D model of the first product for sale is rendered onto the screen. After rendering the first 3D model, a second request to visualize a second product for sale within the physical environment is received during the AR simulation of the first product for sale. In response to the second request, a second 3D model of the second product for sale is rendered onto the screen with the first 3D model.

公开(公告)号：US20200334882A1

公开(公告)日：2020-10-22

申请号：US16903932

申请日：2020-06-17

Applicant: A9.com, Inc.

Inventor： Jesse Chang ,  Jared Corso ,  Xing Zhang ,  Arnab Sanat Kumar Dhua ,  Yu Lou ,  Jason Freund

IPC: G06T11/60 ,  G06T7/13

Abstract: Approaches in accordance with various embodiments provide for the presentation of augmented reality (AR) content with respect to optically challenging surfaces. Such surfaces can be difficult to locate using conventional optical-based approaches that rely on visible features. Embodiments can utilize the fact that horizontal surfaces can be located relatively easily, and can determine intersections or boundaries of those horizontal surfaces that likely indicate the presence of another surface, such as a vertical wall. This boundary can be determined automatically, through user input, or using a combination of such approaches. Once such an intersection is located, a virtual plane can be determined whose relative location to a device displaying AR content can be tracked and used as a reference for displaying AR content.

公开(公告)号：US20200258144A1

公开(公告)日：2020-08-13

申请号：US16272902

申请日：2019-02-11

Applicant: A9.com, Inc.

Inventor： Rupa Chaturvedi ,  Xing Zhang ,  Frank Partalis ,  Yu Lou ,  Colin Jon Taylor ,  Simon Fox

IPC: G06Q30/06 ,  G06Q30/02 ,  G06T19/00 ,  G06N3/08 ,  G06F3/0484 ,  G06T7/50

Abstract: A camera is used to capture image data of representations of a physical environment. Planes and surfaces are determined from a representation. The planes and the surfaces are analyzed using relationships there between to obtain shapes and depth information for available spaces within the physical environment. Locations of the camera with respect to the physical environment are determined. The shapes and the depth information are analyzed using a trained neural network to determine items fitting the available spaces. A live camera view is overlaid with a selection from the items to provide an augmented reality (AR) view of the physical environment from an individual location of the locations. The AR view is enabled so that a user can port to a different location than the individual location by an input received to the AR view while the selection from the items remains anchored to the individual location.